AI Privacy and Confidentiality — Challenges and Opportunities
Supporting the below United Nations Sustainable Development Goals:支持以下聯合國可持續發展目標：支持以下联合国可持续发展目标：
As AI systems become increasingly integrated into real-world applications, they inevitably interact with sensitive and confidential data, raising urgent privacy and security concerns. In this talk, I will focus on two recent lines of work on large language models (LLMs), aiming to both uncover emerging confidentiality risks and design principled defenses. I will conclude with a forward-looking discussion on how advanced AI techniques themselves can be harnessed to enhance data privacy and confidentiality.
Ruihan Wu is a Postdoctoral Researcher at the University of California, San Diego. She received her Ph.D. in Computer Science from Cornell University in 2023 and her B.E. from Tsinghua University in 2018. Her research focuses on privacy and safety in AI, with broader interests in trustworthy and responsible AI. She is a recipient of the 2022 LinkedIn PhD Fellowship and was recognized as a 2025 Rising Star in Data Science.